發(fā)布時間：2018-11-27 07:47

【摘要】：現(xiàn)代化工業(yè)發(fā)展過程中,龐大的數(shù)據(jù)已經(jīng)成為企業(yè)關(guān)注的重要資源,如何安全保存、共享企業(yè)大數(shù)據(jù)資源,挖掘其中潛藏的價值,亟待深入研究。云計算提出了基礎(chǔ)設(shè)施即服務(wù)、平臺即服務(wù)、軟件即服務(wù)的全新服務(wù)模式,適應(yīng)企業(yè)不同階段的需求,為現(xiàn)代化工業(yè)提出了一種全新的發(fā)展模式。本文將云計算技術(shù)與傳統(tǒng)設(shè)備維護(hù)系統(tǒng)相結(jié)合,提出了基于Hadoop的設(shè)備維護(hù)系統(tǒng)云平臺,設(shè)備維護(hù)分布式文件系統(tǒng),設(shè)備維護(hù)分布式計算框架,并分別從設(shè)備維護(hù)資源層、設(shè)備維護(hù)服務(wù)層、設(shè)備維護(hù)應(yīng)用層三個層面對設(shè)備維護(hù)云平臺系統(tǒng)進(jìn)行了詳細(xì)的論述。重點(diǎn)研究了設(shè)備維護(hù)服務(wù)層的設(shè)備故障趨勢預(yù)測模塊,采用支持向量回歸機(jī)算法進(jìn)行故障趨勢預(yù)測,同時分析了參數(shù)C、8、θ對支持向量回歸機(jī)性能產(chǎn)生的不同影響,通過粒子群優(yōu)化算法對支持向量回歸機(jī)進(jìn)行參數(shù)優(yōu)化。采用UCI數(shù)據(jù)庫中的一組標(biāo)準(zhǔn)數(shù)據(jù)集進(jìn)行了優(yōu)化實(shí)驗(yàn)。實(shí)際應(yīng)用中,數(shù)據(jù)規(guī)模逐漸走向巨大化,傳統(tǒng)支持向量回歸機(jī)所需要的時間急劇增加,針對這一問題,提出基于Hadoop環(huán)境下分布式支持向量回歸機(jī)算法。實(shí)驗(yàn)研究表明,基于Hadoop分布式支持向量回歸機(jī)與傳統(tǒng)支持向量回歸機(jī)在預(yù)測性能基本持平的基礎(chǔ)上,大大節(jié)省了計算時間。同時,分析了在保持樣本數(shù)據(jù)不變的情況下,增加Map任務(wù)數(shù)量對時間消耗的影響,得出在一定范圍內(nèi)增加Map任務(wù)數(shù)量會減少時間消耗。建立了基于Hadoop分布式支持向量回歸機(jī)的設(shè)備故障趨勢預(yù)測模型,利用某煤炭企業(yè)采集的設(shè)備振動數(shù)據(jù),對該模型的預(yù)測性能進(jìn)行了驗(yàn)證。結(jié)果表明,基于Hadoop分布式支持向量回歸機(jī)在故障趨勢預(yù)測中具有節(jié)約時間、預(yù)測精度高、可靠性好等特點(diǎn),能夠滿足實(shí)際使用要求。
[Abstract]:In the process of modern industrial development, huge data has become an important resource for enterprises to pay close attention to. How to save and share big data resources of enterprises safely and excavate the hidden value of them is urgent to be deeply studied. Cloud computing proposes a new service model of infrastructure as service, platform as service and software as service, which can meet the needs of enterprises in different stages, and provide a new development model for modern industry. This paper combines cloud computing technology with traditional equipment maintenance system, and puts forward the cloud platform of equipment maintenance system based on Hadoop, the distributed file system of equipment maintenance, the distributed computing framework of device maintenance, and the resource layer of device maintenance, respectively. The equipment maintenance cloud platform system is discussed in detail in three layers: the equipment maintenance service layer and the equipment maintenance application layer. In this paper, the fault trend prediction module of equipment maintenance service layer is studied, and the support vector regression algorithm is used to predict the fault trend. At the same time, the different effects of parameters Cf8 and 胃 on the performance of support vector regression machine are analyzed. The parameters of support vector regression machine are optimized by particle swarm optimization (PSO). A set of standard data sets in UCI database is used to optimize the experiment. In practical application, the data scale is gradually becoming huge, and the time required for traditional support vector regression machines is increasing dramatically. To solve this problem, a distributed support vector regression algorithm based on Hadoop is proposed. The experimental results show that the prediction performance of distributed support vector regression machine based on Hadoop is basically equal to that of traditional support vector regression machine, and the computing time is greatly saved. At the same time, the influence of increasing the number of Map tasks on time consumption is analyzed under the condition of keeping the sample data unchanged, and it is concluded that increasing the number of Map tasks in a certain range will reduce the time consumption. The prediction model of equipment fault trend based on Hadoop distributed support vector regression machine is established. The prediction performance of the model is verified by using the equipment vibration data collected by a coal enterprise. The results show that the distributed support vector regression machine based on Hadoop has the advantages of saving time, high accuracy and good reliability in fault trend prediction, and it can meet the requirements of practical application.
【學(xué)位授予單位】：西安科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：TH17

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳昌運(yùn);李傳慶;;船舶營運(yùn)大數(shù)據(jù)挖掘與應(yīng)用思考[J];船舶與海洋工程;2015年01期

2 景博;湯巍;黃以鋒;楊洲;;故障預(yù)測與健康管理系統(tǒng)相關(guān)標(biāo)準(zhǔn)綜述[J];電子測量與儀器學(xué)報;2014年12期

3 尹振鶴;;云計算的特點(diǎn)及應(yīng)用分析[J];硅谷;2014年23期

4 張黎軍;趙霞;;基于大數(shù)據(jù)分析的旅游管理服務(wù)系統(tǒng)[J];信息通信;2014年11期

5 任仁;;Hadoop在大數(shù)據(jù)處理中的應(yīng)用優(yōu)勢分析[J];電子技術(shù)與軟件工程;2014年15期

6 王繼業(yè);程志華;彭林;周愛華;朱力鵬;;云計算綜述及電力應(yīng)用展望[J];中國電力;2014年07期

7 汪海燕;黎建輝;楊風(fēng)雷;;支持向量機(jī)理論及算法研究綜述[J];計算機(jī)應(yīng)用研究;2014年05期

8 代琨;于宏毅;馬學(xué)剛;李青;;基于支持向量機(jī)的特征選擇算法綜述[J];信息工程大學(xué)學(xué)報;2014年01期

9 龔強(qiáng);;國外云計算發(fā)展現(xiàn)狀綜述[J];信息技術(shù);2013年06期

10 成靜靜;;基于Hadoop的分布式云計算/云存儲方案的研究與設(shè)計[J];數(shù)據(jù)通信;2012年05期

，

本文編號：2359930